基于事理图谱的城市轨道交通系统暴雨灾害链辨识

doi:10.16265/j.cnki.issn1003-3033.2026.04.1718

摘要/Abstract

摘要：

为科学辨识城市轨道交通系统暴雨灾害链中的关键致灾因子及关键致灾路径,提升城市轨道交通系统韧性,基于2010—2024年有关城市轨道交通系统暴雨灾害新闻报道文本数据,综合运用自然语言处理技术、基于规则的模板匹配方法抽取灾害因果事件对;利用t分布随机邻域嵌入(t-SNE)方法对所抽取的事件对进行聚类泛化,构建城市轨道交通系统暴雨灾害抽象事理图谱,结合Gephi将其可视化为灾害链演化网络;引入复杂网络理论定量分析城市轨道交通系统暴雨灾害链演化网络,识别灾害链中的关键致灾因子及关键致灾路径。研究结果表明:暴雨、车站积水、地铁停运及设备故障这4类灾害事件的重要程度较高,为该城市轨道交通系统暴雨灾害链演化网络中的关键致灾因子;道路积水→车站积水、地铁停运→经济损失及道路积水→雨水倒灌这3条演化路径的脆弱性较高,为该城市轨道交通系统暴雨灾害链演化网络中的关键致灾路径。

关键词: 事理图谱, 城市轨道交通, 暴雨灾害链, 复杂网络, 因果关系

Abstract:

In order to scientifically identify the key disaster-causing factors and key disaster-causing paths in the urban rail transit system's flood disaster chain, and enhance the resilience of these systems, a study was conducted based on news report text data related to the urban rail transit flood disasters from 2010 to 2024. Natural language processing technology and a rule-based template matching method were used to extract causal event pairs. The t-Distributed Stochastic Neighbor Embedding (t-SNE) method was used to generalize the extracted event pairs, and the abstract event evolutionary graph of rainstorm disaster in the urban rail transit system was constructed, which was visualized as a disaster chain evolution network combined with Gephi. The complex network theory was introduced to quantitatively analyze the rainstorm disaster chain evolution network of the urban rail transit system, and identify the key disaster factors and key disaster paths in the disaster chain. The results show that the four types of disaster events, rainstorm, station water, subway shutdown and equipment failure, are of high importance and are the key disaster factors in the rainstorm disaster chain evolution network of the urban rail transit system. The three evolutionary paths of "road water → station water", "subway shutdown → economic loss" and "road water → rainwater backpouring" have high vulnerability, which are the key disaster paths in the rainstorm disaster chain evolution network of the urban rail transit system. The identified key disaster-causing factors and key disaster-causing paths can provide decision support for disaster prevention and mitigation.

Key words: urban rail transit, event evolutionary graph, rainstorm disaster chain, complex network, causality

中图分类号:

X915.5
U298

汤洪霞, 王晓洁, 李梦笛, 邵志国. 基于事理图谱的城市轨道交通系统暴雨灾害链辨识[J]. 中国安全科学学报, 2026, 36(4): 252-261.

TANG Hongxia, WANG Xiaojie, LI Mengdi, SHAO Zhiguo. Identification of rainstorm disaster chain in urban rail transit system based on event evolutionary graph[J]. China Safety Science Journal, 2026, 36(4): 252-261.

图/表 13

表1

表2

图1

图2

图3

图4

图5

表3

图6

图7

图8

图9

表4

参考文献 21

[1]	宋英华, 韩保帅, 郭晨. 考虑洪涝灾害风险的县域应急避难场所选址模型[J]. 中国安全科学学报, 2024, 34(4): 191-198. doi: 10.16265/j.cnki.issn1003-3033.2024.04.6850
	Song Yinghua, Han Baoshuai, Guo Chen. Location selection model of emergency shelter considering risk of flood disaster in county[J]. China Safety Science Journal, 2024, 34(4): 191-198. doi: 10.16265/j.cnki.issn1003-3033.2024.04.6850
[2]	Zhang Limao, Liu Mengjie, Wu Xianguo, et al. Simulation-based route planning for pedestrian evacuation in metro stations: a case study[J]. Automation in Construction, 2016, 71: 430-442. doi: 10.1016/j.autcon.2016.08.031
[3]	Markolf S A, Hoehne C, Fraser A, et al. Transportation resilience to climate change and extreme weather events-Beyond risk and robustness[J]. Transport Policy, 2019, 74: 174-186. doi: 10.1016/j.tranpol.2018.11.003
[4]	Li Hongwei, Wang Yuxi, Xing Yingying, et al. Contributing factors affecting the severity of metro escalator injuries in the Guangzhou metro, China[J]. International Journal of Environmental Research and Public Health, 2021, 18(2): 1-15. doi: 10.3390/ijerph18010001
[5]	Jiao Liudan, Luo Qiudie, Lu Hao, et al. Research on the urban rail transit disaster chain: critical nodes, edge vulnerability and breaking strategy[J]. International Journal of Disaster Risk Reduction, 2024, 102: DOI: 10.1016/j.ijdrr.2024.104258.
[6]	焦柳丹, 常星宇, 霍小森, 等. 基于贝叶斯网络的城市轨道交通设备故障灾害链风险概率研究[J]. 铁道标准设计, 2025, 69(6): 68-76.
	Jiao Liudan, Chang Xingyu, Huo Xiaosen, et al. Study on risk probability of equipment fault disaster chains in urban rail transit based on bayesian network[J]. Railway Standard Design, 2025, 69(6): 68-76.
[7]	Li Zhongyang, Zhao Sendong, Ding Xiao, et al. Eeg: knowledge base for event evolutionary principles and patterns[C]. Chinese National Conference on Social Media Processing, 2017: 40-52.
[8]	杨纪星, 杨波, 朱剑林, 等. 金融领域事件因果关系发现及事理图谱构建与应用[J]. 中文信息学报, 2023, 37(7): 131-142.
	Yang Jixing, Yang Bo, Zhu Jianlin, et al. Event causality extraction, eventic graph construction and application in financial domain[J]. Journal of Chinese Information Processing, 2023, 37(7): 131-142.
[9]	肖亚龙, 冯皓, 朱承璋, 等. 面向复杂网络舆情知识发现的事理图谱方法优化研究[J]. 情报杂志, 2024, 43(10): 134-143.
	Xiao Yalong, Feng Hao, Zhu Chengzhang, et al. Optimization of event evolutionary graph method for complex online public opinion knowledge discovery[J]. Journal of Intelligence, 2024, 43(10): 134-143.
[10]	李诗轩. 基于事理图谱的公共卫生事件次生衍生事件预警模型构建研究[J]. 中国安全生产科学技术, 2024, 20(3): 12-19.
	Li Shixuan. Construction of early-warning model for secondary and derivative events of public health emergencies based on event evolutionary graph[J]. Journal of Safety Science and Technology, 2024, 20(3): 12-19.
[11]	冯钧, 王云峰, 邬炜, 等. 城市内涝事理图谱构建方法及应用[J]. 河海大学学报:自然科学版, 2020, 48(6): 479-487.
	Feng Jun, Wang Yunfeng, Wu Wei, et al. Construction method and application of event logic graph for urban waterlogging[J]. Journal of Hohai University:Natural Sciences, 2020, 48(6): 479-487.
[12]	李红儒, 栾婷婷, 邓明月, 等. 面向危险化学品事故的事理图谱构建[J]. 中国安全科学学报, 2024, 34(5): 195-203. doi: 10.16265/j.cnki.issn1003-3033.2024.05.1570
	Li Hongru, Luan Tingting, Deng Mingyue, et al. Development of causal graph for hazardous chemical accidents[J]. China Safety Science Journal, 2024, 34(5): 195-203. doi: 10.16265/j.cnki.issn1003-3033.2024.05.1570
[13]	Che Wanxiang, Feng Yunlong, Qin Libo, et al. N-LTP: an open-source neural language technology platform for Chinese[C]. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2021: 42-49.
[14]	王毅, 沈喆, 姚毅凡, 等. 领域事件图谱构建方法综述[J]. 数据分析与知识发现, 2020, 4(10): 1-13. doi: 10.11925/infotech.2096-3467.2020.0383
	Wang Yi, Shen Zhe, Yao Yifan, et al. Domain-Specific event graph construction methods: a review[J]. Data Analysis and Knowledge Discovery, 2020, 4(10): 1-13. doi: 10.11925/infotech.2096-3467.2020.0383
[15]	赵海宾, 邵彩虹, 李小龙. 事件关系抽取方法综述[J]. 计算机技术与发展, 2024, 34(12): 1-8.
	Zhao Haibin, Shao Caihong, LI Xiaolong. A review of event relationship extraction methods[J]. Computer Technology and Development, 2024, 34(12): 1-8.
[16]	裘江南. 汉语文本中突发事件因果关系抽取方法研究[D]. 大连: 大连理工大学, 2012.
	Qiu Jiangnan. Research on emergency causality extraction from chinese corpus[D]. Dalian: Dalian University of Technology, 2012.
[17]	彭湃. 现代汉语因果关系连接成分研究综述[J]. 汉语学习, 2004(2): 44-48.
[18]	Zhao Sendong, Wang Quan, Massung S, et al. Constructing and embedding abstract event causality networks from text snippets[C]. The Tenth ACM International Conference. ACM, 2017: 335-344.
[19]	于凯, 杨富义. 基于事理图谱的突发事件网络舆情演化模型构建[J]. 上海理工大学学报, 2023, 45(1): 27-35.
	Yu Kai, Yang Fuyi. Construction of an evolution model of emergency network public opinion based on event knowledge graph[J]. Journal of University of Shanghai for Science and Technology, 2023, 45(1): 27-35.
[20]	李晓璐, 于昕明, 雷方舒, 等. 城市轨道交通系统灾害链网络模型构建与评价[J]. 中国安全科学学报, 2018, 28(6): 179-184. doi: 10.16265/j.cnki.issn1003-3033.2018.06.030
	Li Xiaolu, Yu Xinming, Lei Fangshu, et al. Construction of disaster chain network model and evaluation of network index for urban rail transit system[J]. China Safety Science Journal, 2018, 28(6): 179-184. doi: 10.16265/j.cnki.issn1003-3033.2018.06.030
[21]	刘高峰, 李佳静, 王慧敏, 等. 城市暴雨洪涝灾害链辨识及系统性风险评估[J]. 中国管理科学, 2025, 33(7): 222-231.
	Liu Gaofeng, Li Jiajing, Wang Huimin, et al. Identification of urban rainstorm flood disaster chain and assessment of systematic risk[J]. Chinese Journal of Management Science, 2025, 33(7): 222-231.

词性	因果提示词
连词	由于、因为、因、何以、为此
动词	引发、导致、造成、已致、致、使得、致使、突发、突遭、遭受、遭遇
动词词组	<受…影响>,<因…影响>,<受…冲击>
动词连词组合或连词组合	<由于,造成>,<由于,导致>,<遭遇,引发>,<遭遇,导致>, <因为,导致>,<因,导致>,<因,致>,<因,引发>,<因,造成>,<因,所致>
名词	原因
动词名词组合	<造成,原因>

规则	因果提示词	句法模板	优先级
由因到果前端式	由于、因为、因	<Conj>{Cause},{Effect}	7
由因到果居中式明确	造成、致、导致、引发、由于等	{Cause}<Conj/Verb>{Effect}	8
由因到果前端配套式	<受…影响>,<因…影响>	<Conj>{Cause}<Verb>,{Effect}	5
由因到果居中配套式	<由于,造成>,<由于,导致><因为,导致>, <因,导致>,<因,致>,<因,引发>等。	<Conj>{Cause}<Conj/Verb>{Effect}	4
由果溯因居中配套式	<造成,原因>	<Conj…>{Effect}<Conj…>{Cause}	6
由因到果居中引导二层因果关系	配套动词连词对加因果提示动词	<Conj>{Cause1}<Conj/Verb>, {Effect1/cause2},<verb>{effect2}	1
由因到果居中动词引导二层因果关系	二元因果提示动词	{Cause1}<verb>{effect1/Cause2}, <verb>{effect2/cause2}	2
由因到果前端连词引导二层因果关系	因果提示词连词加因果提示词动词	<Conj>{Cause1},{Effect1/cause2}, <verb>{effect2}	3

基本特征	值
节点数/个	17
边数/条	69
密度	0.254
平均度	4.059
平均路径长度	1.159
聚类系数	0.340

边脆弱性排名	边	B_ij	L_ij	H_ij	V_ij
1	道路积水→车站积水	6	1.170 7	1	7.024 4
2	地铁停运→经济损失	6	1.139 2	1	6.835 4
3	道路积水→雨水倒灌	5	1.160 5	1	5.802 5
4	车站积水→经济损失	4	1.170 7	1	4.682 9
5	异物入侵→设备故障	4	1.139 2	1	4.557 0